The La Moulinette AI blog
Article series on building AI systems: what the law requires, what to settle before picking a model, and how to check the result holds up.
Brick by brick
My first project doesn't build anything
It reads code someone else already wrote, measures what state it's in, and says where to start. Why this brick comes before all the others.
Read the article arrow_forwardAn answer that cites its sources, or says nothing
Why I put my first complete system on the most demanding ground I know: a field where a plausible but wrong answer costs more than silence.
Read the article arrow_forwardA good answer addressed to nobody
The real bottleneck in an AI project isn't the model's intelligence, it's the state of whatever you want to plug it into. Demonstrated in the best-equipped sector there is.
Read the article arrow_forwardThe only project that had users
Twenty months, five applications, and the discovery that what people adopt is never what took longest to build.
Read the article arrow_forwardThe model is the last question
Four questions to ask before opening a single piece of technical documentation. And what happens when you don't ask them.
Read the article arrow_forward
Take back control
Take back control: how to get started with sovereign AI in Europe in 2026
The 2026 landscape of sovereign AI in Europe and the UK: a roadmap, the hybrid API/self-hosting strategy, and why sovereignty is not the same as data location.
Read the article arrow_forwardThe AI Act explained for people with no time: what Europe really expects of you
The EU AI Act without the jargon: what it expects of your business, the risk tiers, the timeline, and how the UK's approach differs. The pitfalls to avoid.
Read the article arrow_forwardGDPR, the sequel: you thought you were done with it? Your AI projects bring it right back.
GDPR and AI, EU and UK: legal bases, DPIAs, data-subject rights. A practical playbook to run AI projects without a legal misstep.
Read the article arrow_forwardBuilding your first sovereign AI agent: the guide for people who take action
Build your first sovereign AI agent in seven steps: the five building blocks, the budgets, the open-source tools, and the pitfalls to avoid along the way.
Read the article arrow_forwardScaling up: the guide for those whose agent succeeded
Scaling your AI agent: concurrent users, model choice, local vs API, with the numbers to make the call in a budget meeting.
Read the article arrow_forward